PyPI page
Home page
Author:
Emmett McFarlane
Summary:
Get clean data from tricky documents, powered by VLMs.
Latest version:
1.7.2
Required dependencies:
beautifulsoup4
|
magika
|
markdownify
|
moviepy
|
numpy
|
openai
|
openpyxl
|
pandas
|
pillow
|
playwright
|
pydantic
|
pymupdf
|
pymupdf4llm
|
python-docx
|
python-dotenv
|
python-pptx
|
pytube
|
requests
Optional dependencies:
llama-index
|
openai-whisper
|
sentence-transformers
|
torch
|
torchaudio
|
torchvision
Downloads last day:
15
Downloads last week:
95
Downloads last month:
1,043